简体   繁体   English

深度学习用于服装和鞋子的模式识别

[英]Deep learning for pattern recognition for clothes and shoes

I am newbie in deep learning, so not sure about the ability of deep learning. 我是深度学习的新手,因此不确定深度学习的能力。 I am wondering if it is possible to use DL for pattern recognition. 我想知道是否可以使用DL进行模式识别。 More specific, given many images containing different people wearing the same clothes or shoes. 更具体地讲,给定许多图像包含穿着相同衣服或鞋子的不同人物。 Can we tell it out that certain patterns in these images are the same, ie wearing the same clothes or shoes? 我们能否说出这些图像中的某些图案是相同的,即穿着相同的衣服或鞋子?

If yes, what is the pipeline to do it? 如果是,执行该操作的管道是什么? From the beginning of data preparation to the end of classification/prediction? 从数据准备的开始到分类/预测的结束? Any reference papers or blogs recommended? 有推荐的参考文件或博客吗? Thanks in advance! 提前致谢!

Here are some examples I found online for better illustration: 以下是一些我在网上找到的示例,可以更好地说明问题:

enter link description here 在此处输入链接说明

enter link description here 在此处输入链接说明

From what I could gather from your problem statement, I believe if you require some general similarity you should go for an unsupervised clustering algorithm. 从我从问题陈述中收集的信息来看,我相信如果您需要一些通用的相似性,则应该采用无监督的聚类算法。 It will create groups for your data set based on hidden similarities but you will have to label the clusters yourself which might not be very useful in your case. 它将基于隐藏的相似性为您的数据集创建组,但是您将不得不自己标记集群,这在您的情况下可能不是很有用。

Another approach could be to manually label your images with categories of interest for instance same background, same shoes, same clothes etc and train a multi class convolutional neural network. 另一种方法可能是用感兴趣的类别手动标记图像,例如相同的背景,相同的鞋子,相同的衣服等,并训练多类卷积神经网络。

Neural network would probably give you better results or you can even use the deep feather the neural net learned to extract features from your data and use a clustering algorithm on the extracted features. 神经网络可能会给您带来更好的结果,或者您甚至可以使用神经网络学到的深层羽毛从数据中提取特征,并对提取的特征使用聚类算法。

This is an interesting time to be learning about deep learning. 这是学习深度学习的有趣时机。 These tutorials might help you. 这些教程可能会对您有所帮助。 Let me know if I can help further. 让我知道是否可以进一步提供帮助。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM